Research map / Vision-language and multimodal / Robot action and navigation
Learning Intuitive Physics with Multimodal Generative Models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use final-step rather than multi-step prediction | VAE-visual only · Freefall | visual BCE (×1e-4): 6522 -> 5750 | Helped |
| Use final-step rather than multi-step prediction | MVAE w/ pose · Perturbation | visual BCE (×1e-4): 7552 -> 6054 | Helped |
| Add tactile input to visual-only prediction | MVAE w/ pose · Real dataset | visual BCE (×1e-4): 3532 -> 3509 | Helped |
| Add visual input to tactile-only prediction | MVAE w/ pose · Real dataset | tactile BCE (×1e-4): 2872 -> 2819 | Helped |
| Add pose modality (ablation) | MVAE · Freefall | visual BCE (×1e-4), final-step: 5752 -> 5741 | No clear effect |
| Add pose modality (ablation) | MVAE · Inclined | visual BCE (×1e-4), final-step: 5890 -> 5891 | No clear effect |
| Add pose modality (ablation) | MVAE · Perturbation | visual BCE (×1e-4), final-step: 6095 -> 6054 | Helped |
| Add pose modality (ablation) | MVAE · Inclined | tactile BCE (×1e-4), final-step: 6710 -> 6709 | No clear effect |
Closest papers by meaning
- PhysTacGen: Physics-Aware Visual-Tactile Sensor Image Generation (NeurIPS 2026 · similarity 0.89)
- AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors (ICLR 2025 · similarity 0.89)
- EgoTac: In-the-wild Tactile Prediction from Egocentric Vision (NeurIPS 2026 · similarity 0.88)
- Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper (NeurIPS 2025 · similarity 0.87)
- DIFFTACTILE: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation (ICLR 2024 · similarity 0.87)
- Universal Visuo-Tactile Video Understanding for Embodied Interaction (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.